import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors as mcolors
import matplotlib.ticker as mticker
import mpl_toolkits
from mpl_toolkits.basemap import Basemap
import re
import os
from IPython.display import display, HTML
import warnings

from classifier import Classifier
from constants import *

warnings.simplefilter(action='ignore', category=FutureWarning)
pd.set_option('display.max_rows', 300000)
pd.set_option('display.max_columns', 500)

csvs = sorted(os.listdir(INPUTS_PATH))
csvs

['2014-final.xlsx - Sheet1.csv',
 '2015-final.xlsx - Sheet1.csv',
 '2016-final.xlsx - Total counts.csv',
 '2017-final.xlsx - 2017 LIS phytoplankton count.csv',
 '2018-Final Report Data.xlsx - 2018 LIS phytoplankton count.csv',
 'LIS_2019-Phytoplankton_Final Report Data.xlsx - 2019 LIS phytoplankton count.csv',
 'LIS_2020-Phytoplankton_Final Report Data.xlsx - 2020 LIS phytoplankton count.csv',
 'LIS_2021-Phytoplankton_Final Report Data.xlsx - 2021 LIS phytoplankton count.csv']

season2month = {
    'Winter': ['January', 'February', 'March'],
    'Spring': ['April', 'May', 'June'],
    'Summer': ['July', 'August', 'September'],
    'Fall': ['October', 'November', 'December']
}

season2boundary = {    
    'Winter': (0, 1750000),
    'Spring': (0, 2250000),
    'Summer': (0, 3000000),
    'Fall': (0, 500000)
}

def sort_mixoplankton_type_by_season(season, csv_name):
    months = season2month.get(season)
    
    classified = Classifier(csv_name)
    df = classified.add_multiheader(classified.mixoplankton)
    df = pd.concat([df.loc[:, df.columns.get_level_values(2).isin(['MFT'])], df.loc[:, df.columns.get_level_values(0).isin(months)]], axis=1)
    df = df.loc[~(df.loc[:, df.columns.get_level_values(0).isin(months)] == 0).all(axis=1)]
    df.columns = df.columns.get_level_values(1)
    df = pd.concat([df[[np.nan]], df.groupby(df.columns.str[0], axis=1).sum()], axis=1).rename(columns= {np.nan:'MFT'})
    df = df.groupby('MFT').sum().reset_index()
    df['Totals'] = df.iloc[:, 1:].sum(axis=1)
    df['Percentages'] = ((df['Totals'] / df['Totals'].sum()) * 100)
    
    return df

What different types of mixoplankton are found by station every year?

def display_tables_by_season(season):
    for csv_name in csvs:
        # Get year
        year = re.search(r'\b(\d{4})\b', csv_name).group(1) if re.search(r'\b(\d{4})\b', csv_name) else 'Year not found'
    
        # Get table for each year
        display(HTML(f"<h2>Mixoplankton Functional Type in LIS in {season} of {year}</h2>"))
        display(sort_mixoplankton_type_by_season(season, csv_name))

display_tables_by_season('Winter')

Mixoplankton Functional Type in LIS in Winter of 2014

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1636800	595452	638000	580800	110836	36652	155452	124036	140756	51260	4070044	100.0

Mixoplankton Functional Type in LIS in Winter of 2015

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	409200	303600	208252	378400	343200	387200	354904	217008	243408	117304	2962476	100.0

Mixoplankton Functional Type in LIS in Winter of 2016

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	77704	225852	215600	39556	24904	104104	200904	181852	52800	26400	1149676	100.0

Mixoplankton Functional Type in LIS in Winter of 2017

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	167156	79156	70356	123156	43956	39600	33704	29304	38060	1452	625900	100.0

Mixoplankton Functional Type in LIS in Winter of 2018

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	487564	324104	543312	406208	322608	205260	349756	146608	15312	112860	2913592	99.879333
1	pSNCM	704	704	0	1408	0	0	704	0	0	0	3520	0.120667

Mixoplankton Functional Type in LIS in Winter of 2019

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	198308	217008	103004	305052	294008	220000	210408	168564	123332	66000	1905684	99.923865
1	pSNCM	0	0	0	0	0	0	0	1452	0	0	1452	0.076135

Mixoplankton Functional Type in LIS in Winter of 2020

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	215600	683540	767052	349052	206008	142604	340560	60720	145288	63756	2974180	99.997041
1	pSNCM	0	88	0	0	0	0	0	0	0	0	88	0.002959

Mixoplankton Functional Type in LIS in Winter of 2021

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	224400	127600	242000	212652	120252	178904	391600	200904	19008	168696	1886016	100.0

display_tables_by_season('Spring')

Mixoplankton Functional Type in LIS in Spring of 2014

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1739136	1999008	1506252	2230756	1865600	853512	2069018	1047156	1033956	852060	15196454	100.0

Mixoplankton Functional Type in LIS in Spring of 2015

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1296504	1856800	1140480	833052	805200	1918356	645304	569052	768504	475200	10308452	100.0

Mixoplankton Functional Type in LIS in Spring of 2016

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	668800	595452	302104	881452	92356	231704	121704	274252	180356	85052	3433232	99.324075
1	pSNCM	0	10252	4400	1452	1452	0	2904	1452	1452	0	23364	0.675925

Mixoplankton Functional Type in LIS in Spring of 2017

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	978252	539704	427548	698104	582252	305052	363704	145156	594000	119416	4753188	99.90844
1	pSNCM	0	1452	2904	0	0	0	0	0	0	0	4356	0.09156

Mixoplankton Functional Type in LIS in Spring of 2018

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1201200	1118304	1633852	486156	528000	638704	563200	775104	262504	181852	7388876	98.975641
1	pSNCM	0	704	2904	704	0	704	0	704	0	352	6072	0.081336
2	pSNCM*	0	0	0	70400	0	0	0	0	0	0	70400	0.943024

Mixoplankton Functional Type in LIS in Spring of 2019

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	888800	690756	447304	682000	632104	378708	425304	689304	461956	189904	5486140	99.996792
1	pSNCM	0	0	176	0	0	0	0	0	0	0	176	0.003208

Mixoplankton Functional Type in LIS in Spring of 2020

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages

Mixoplankton Functional Type in LIS in Spring of 2021

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	836088	1584176	729256	476652	497552	536800	718564	520608	375012	141152	6415860	99.998628
1	pSNCM	88	0	0	0	0	0	0	0	0	0	88	0.001372

display_tables_by_season('Summer')

Mixoplankton Functional Type in LIS in Summer of 2014

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1887556	1057408	690712	772904	551452	450208	494208	285956	488356	300476	6979236	99.791131
1	pSNCM	2904	4400	4400	0	0	2904	0	0	0	0	14608	0.208869

Mixoplankton Functional Type in LIS in Summer of 2015

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	514800	1149412	968880	819720	499840	602800	378792	283800	83600	45408	5347052	99.754562
1	pSNCM	0	5852	5852	0	1452	0	0	0	0	0	13156	0.245438

Mixoplankton Functional Type in LIS in Summer of 2016

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	639452	376904	708400	343156	107052	177452	189200	664356	0	86460	3292432	98.169844
1	pSNCM	11704	5808	5808	4356	10252	14652	0	8800	0	0	61380	1.830156

Mixoplankton Functional Type in LIS in Summer of 2017

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1962400	3212704	1264252	956252	1088252	516956	651904	835966	285956	286660	11061302	99.925273
1	pSNCM	1452	704	2156	1452	0	0	0	1452	1056	0	8272	0.074727

Mixoplankton Functional Type in LIS in Summer of 2018

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1148752	2011108	1259104	696652	1004652	381304	112156	153956	204160	145904	7117748	99.709686
1	pSNCM	704	3608	1408	352	1452	13200	0	0	0	0	20724	0.290314

Mixoplankton Functional Type in LIS in Summer of 2019

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1009052	827112	1074260	652652	476652	500104	462176	381304	283140	151228	5817680	98.908580
1	eSNCM	0	0	0	0	0	0	30800	792	6028	176	37796	0.642584
2	pSNCM	3784	13200	1584	0	1452	5852	176	352	0	0	26400	0.448836

Mixoplankton Functional Type in LIS in Summer of 2020

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1487200	1478444	1166704	912252	1776280	1682252	1255452	1307020	217140	164956	11447700	99.930480
1	eSNCM	0	0	0	0	0	0	0	0	0	1452	1452	0.012675
2	pSNCM	0	88	2904	2904	88	0	176	176	88	88	6512	0.056845

Mixoplankton Functional Type in LIS in Summer of 2021

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	1582812	1705704	1150204	818400	611908	792000	240504	363704	780208	37004	8082448	99.90917
1	pSNCM	704	2156	2904	1056	0	352	0	0	88	88	7348	0.09083

display_tables_by_season('Fall')

Mixoplankton Functional Type in LIS in Fall of 2014

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	580800	780252	503052	181852	219956	522060	601304	372504	95304	41008	3898092	99.962765
1	pSNCM	0	0	0	0	0	0	0	1452	0	0	1452	0.037235

Mixoplankton Functional Type in LIS in Fall of 2015

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	514800	498652	616000	435600	130504	151052	61600	154880	37532	11704	2612324	100.0

Mixoplankton Functional Type in LIS in Fall of 2016

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	72556	71852	23408	114312	39556	136400	30756	123156	32252	39556	683804	99.788108
1	pSNCM	0	1452	0	0	0	0	0	0	0	0	1452	0.211892

Mixoplankton Functional Type in LIS in Fall of 2017

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	417956	435556	328504	221452	216260	100408	212652	102608	199408	53416	2288220	99.875168
1	pSNCM	0	0	0	0	1452	0	0	704	0	0	2156	0.094104
2	pSNCM*	0	0	0	0	704	0	0	0	0	0	704	0.030728

Mixoplankton Functional Type in LIS in Fall of 2018

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	459008	99660	250756	145860	269848	107228	71808	35156	3784	4356	1447464	99.975688
1	pSNCM	0	0	0	0	0	0	0	0	352	0	352	0.024312

Mixoplankton Functional Type in LIS in Fall of 2019

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	215600	285912	591008	277508	195756	205568	305228	96712	90112	4708	2268112	99.961216
1	pSNCM	0	0	176	176	0	352	176	0	0	0	880	0.038784

Mixoplankton Functional Type in LIS in Fall of 2020

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	199628	71852	145200	4400	89452	58696	52800	57904	66396	1540	747868	99.994117
1	pSNCM	0	0	0	0	0	0	0	0	0	44	44	0.005883

Mixoplankton Functional Type in LIS in Fall of 2021

	MFT	A	B	C	D	E	F	H	I	J	K	Totals	Percentages
0	CM	129756	199496	138512	24860	30756	38016	134948	110704	17908	5940	830896	100.0

# creates basemap for mixoplankton given dataframe df, tickmark boundary, and title 
def make_basemap(df, boundary, title, scattercolumn='Totals'):
    vmin, vmax = boundary
    
    coord = pd.read_csv('LIS_CELLCOUNTS_2019 + Station Coords.csv')
    coord = coord.fillna(0)
    coords = coord[['ST', 'lat', 'lon']].drop_duplicates()
    coords = pd.concat([df, coords], axis=1).drop(['ST'], axis=1)
    x, y = (coords['lon'].tolist(), coords['lat'].tolist())
    
    # Create Basemap and color bar
    fig, ax = plt.subplots(figsize=(10, 10))
        
    # Create a Basemap instance
    map = Basemap(projection='cyl', lon_0=-73, lat_0=41, llcrnrlat=40.7, urcrnrlat=41.3, llcrnrlon=-74, urcrnrlon=-72, resolution='f', ax=ax)
    
    # Add map features
    map.drawmapboundary()
    map.fillcontinents()
    map.drawcoastlines()
    map.drawparallels(np.arange(40.7, 41.3, .15), labels=[1, 1, 1, 1])
    map.drawmeridians(np.arange(-74, -72, .25), labels=[1, 1, 1, 1])
    
    # Scatter plot on the Basemap
    sc = map.scatter(x, y, c=coords[scattercolumn], s=100, cmap='rainbow', edgecolor='black', zorder=5, norm=mcolors.Normalize(vmin=vmin, vmax=vmax))
        
    # Color Bar
    cbar = plt.colorbar(sc, ax=ax, orientation="vertical", shrink=0.25, aspect=8, pad=0.1) 
    cbar.set_ticks(np.linspace(vmin, vmax, 11))
    cbar.set_ticklabels([f'{int(tick):,}' for tick in np.linspace(vmin, vmax, 11)])
        
    fig.suptitle(title, fontsize=20, y=0.64)

    coords = coords.drop(['lat', 'lon'], axis=1).set_index('Station').transpose()

    plt.show()
    display(coords)

# creates a season map for mixoplankton based on elevation ("bottom" or "surface") and season
def make_season_map(elevation, season, csv_name):
    if elevation == "bottom":
        elevation_var = "B"
    elif elevation == "surface":
        elevation_var = "S"
    else:
        raise ValueError(f"Invalid elevation: {elevation}.")
        
    months = season2month.get(season)
    vmin, vmax = season2boundary.get(season)

    classified = Classifier(csv_name)
    df = classified.add_multiheader(classified.mixoplankton)
    df = df.loc[:, df.columns.get_level_values(0).isin(months)]
    df.columns = df.columns.get_level_values(1)
    df = df.groupby(df.columns.str[:3], axis=1).sum()
    df = pd.DataFrame(df.sum()).reset_index().rename(columns={0: 'Totals', 'index': 'Station'})
    df = df[df['Station'].str[2] == elevation_var].reset_index(drop=True)

    year = re.search(r'\b(\d{4})\b', csv_name).group(1) if re.search(r'\b(\d{4})\b', csv_name) else 'Year not found'

    make_basemap(df, (vmin, vmax), f'{elevation.capitalize()} Mixoplankton {season} {year}')

for csv_name in csvs:
    # Get map for each season
    for season in season2month.keys():
        make_season_map('surface', season, csv_name)
        make_season_map('bottom', season, csv_name)

def display_figures_by_season(season):
    for csv_name in csvs:
        make_season_map('surface', season, csv_name)
        make_season_map('bottom', season, csv_name)

display_figures_by_season("Winter")

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1636800	595452	638000	580800	110836	36652	155452	124036	140756	51260

Station	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
Totals	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	167200	44000	61600	184800	123200	162800	134904	211200	192104	29304

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	242000	259600	146652	193600	220000	224400	220000	5808	51304	88000

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	42504	105600	96800	2904	23452	41052	127600	88000	52800	17600

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	35200	120252	118800	36652	1452	63052	73304	93852	0	8800

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	114400	58652	27852	46904	32252	13200	2904	11704	16104	1452

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	52756	20504	42504	76252	11704	26400	30800	17600	21956	0

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	198704	232408	349052	206800	211904	64504	101904	101904	10252	44000

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	289564	92400	194260	200816	110704	140756	248556	44704	5060	68860

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	108856	117304	54604	49852	13904	154000	133452	124608	111452	66000

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	89452	99704	48400	255200	280104	66000	76956	45408	11880	0

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	154000	550176	445852	133452	118008	103004	160160	32428	127688	24156

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	61600	133452	321200	215600	88000	39600	180400	28292	17600	39600

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	57200	8800	118800	107052	14652	158400	105600	63052	9504	61644

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	167200	118800	123200	105600	105600	20504	286000	137852	9504	107052

display_figures_by_season("Spring")

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1739136	1999008	1506252	2230756	1865600	853512	2069018	1047156	1033956	852060

Station	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
Totals	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	423852	479600	466400	435600	343200	1029600	416504	303600	335852	321200

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	872652	1377200	674080	397452	462000	888756	228800	265452	432652	154000

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	457600	331452	139304	639452	41008	95304	61556	123200	46904	39600

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	211200	274252	167200	243452	52800	136400	63052	152504	134904	45452

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	624800	293304	200904	256652	140800	105600	120252	111452	360800	62260

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	353452	247852	229548	441452	441452	199452	243452	33704	233200	57156

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	365200	507408	662904	358556	444400	313104	277200	357104	215600	85052

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	836000	611600	973852	198704	83600	326304	286000	418704	46904	97152

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	228800	400400	270028	356400	209704	38456	211200	381304	189156	132000

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	660000	290356	177452	325600	422400	340252	214104	308000	272800	57904

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	0	0	0	0	0	0	0	0	0	0

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	0	0	0	0	0	0	0	0	0	0

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	655776	1020976	526856	369600	193952	171600	324808	102608	182908	70752

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	180400	563200	202400	107052	303600	365200	393756	418000	192104	70400

display_figures_by_season("Summer")

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1170356	818400	508904	626252	349052	328460	360756	108504	243452	99616

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	720104	243408	186208	146652	202400	124652	133452	177452	244904	200860

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	426800	896104	885852	466400	388652	484000	112904	70400	66000	23408

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	88000	259160	88880	353320	112640	118800	265888	213400	17600	22000

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	167156	217008	470756	214060	41052	101200	167200	640904	0	60060

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	484000	165704	243452	133452	76252	90904	22000	32252	0	26400

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1295052	2803504	1231208	630652	866800	141504	541200	545566	240504	272800

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	668800	409904	35200	327052	221452	375452	110704	291852	46508	13860

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	621456	1727264	1203312	541552	894652	330000	59356	139304	90904	115104

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	528000	287452	57200	155452	111452	64504	52800	14652	113256	30800

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	835384	696608	990792	366652	297704	466356	255376	313544	154176	118976

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	177452	143704	85052	286000	180400	39600	237776	68904	134992	32428

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1443200	1249732	830808	579304	1663376	1299452	1029688	620576	110176	64504

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	44000	228800	338800	335852	112992	382800	225940	686620	107052	101992

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	1103960	1236708	975656	317856	79200	589996	215600	281600	758296	36740

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	479556	471152	177452	501600	532708	202356	24904	82104	22000	352

display_figures_by_season("Fall")

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	356400	357852	230252	63052	80652	265408	494252	237556	20504	7304

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	224400	422400	272800	118800	139304	256652	107052	136400	74800	33704

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	470800	463452	431200	316800	107052	52800	52800	119680	37532	10252

Station	A4B	B3B	C1B	D1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	44000	35200	184800	88000	30800	23452	98252	8800	35200	0	1452

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	32252	45452	16104	71808	29304	35200	27852	114356	17600	2904

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	40304	27852	7304	42504	10252	101200	2904	8800	14652	36652

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	343156	275704	249304	79200	116512	27104	96800	71104	109956	24904

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	74800	159852	79200	142252	101904	73304	115852	32208	89452	28512

Station	A4S	B3S	C1S	D3S	E1S	F2S	FBS	H4S	I2S	J2S	K2S
Totals	214104	82104	228756	34408	221452	54252	17776	68904	26356	3432	4356

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	244904	17556	22000	111452	48396	35200	2904	8800	704	0

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	165704	234608	434280	242176	146652	139832	186428	68904	20504	1628

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	49896	51304	156904	35508	49104	66088	118976	27808	69608	3080

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	111628	49852	114400	4400	66000	27852	22000	35552	66396	1452

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	88000	22000	30800	0	23452	30844	30800	22352	0	132

Station	A4S	B3S	C1S	D3S	E1S	F2S	H4S	I2S	J2S	K2S
Totals	89452	58696	129360	11748	17556	29304	55748	97152	14652	88

Station	A4B	B3B	C1B	D3B	E1B	F2B	H4B	I2B	J2B	K2B
Totals	40304	140800	9152	13112	13200	8712	79200	13552	3256	5852

What is the percentage of mixoplankton at each station? (maps)

def seasonal_trophic_strategy_per_station(csv_name, season):

    # Get months corresponding to season
    months = season2month.get(season)
    
    # Clean data
    classified = Classifier(csv_name)
    by_station_SB = classified.add_multiheader(classified.all_classified)
    removed_columns = by_station_SB.loc[:, by_station_SB.columns.get_level_values(2).isin(['Status', 'Phylum', 'Genus', 'Species'])].copy()
    removed_columns.columns = removed_columns.columns.get_level_values(2)
    other_columns = by_station_SB.loc[:, ~by_station_SB.columns.get_level_values(2).isin(['Status', 'Phylum', 'Genus', 'Species', 'Totals'])]
    other_columns = other_columns.loc[:, other_columns.columns.get_level_values(0).isin(months)]
    other_columns.columns = other_columns.columns.get_level_values(1)
    other_columns = other_columns.groupby(other_columns.columns.str[0], axis=1).sum()
    by_station_SB = pd.concat([removed_columns, other_columns ], axis=1)
    by_station_SB = by_station_SB.drop(['Phylum', 'Genus', 'Species'], axis=1).replace('Yes', 'Mixoplankton').groupby('Status').sum()
    by_station_SB.index.name = None
    by_station_SB = by_station_SB.transpose().reset_index().rename(columns={"index": "Station"})
    by_station_SB['Totals'] = by_station_SB[['Mixoplankton', 'No']].sum(axis=1)
    by_station_SB['Mixoplankton %'] = by_station_SB['Mixoplankton'].div(by_station_SB['Mixoplankton'].sum(), axis=0) * 100
    by_station_SB = by_station_SB.drop(['Mixoplankton', 'No', 'Totals'], axis=1)
    
    # Get year
    year = re.search(r'\b(\d{4})\b', csv_name).group(1) if re.search(r'\b(\d{4})\b', csv_name) else 'Year not found'

    make_basemap(by_station_SB, (0, 100), f'Percentage of Mixoplankton by Station {season} {year}', scattercolumn='Mixoplankton %')
        
    plt.show()

for csv_name in csvs:
    # Get map for each season
    for season in season2month.keys():
        seasonal_trophic_strategy_per_station(csv_name, season)

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	40.215781	14.630112	15.675506	14.270116	2.723214	0.900531	3.819418	3.047535	3.458341	1.259446

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	11.444354	13.154437	9.911865	14.679451	12.276548	5.616521	13.615137	6.890792	6.803929	5.606966

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	27.030343	15.182037	9.938912	11.051204	7.88482	6.478726	7.066329	4.088681	6.982655	4.296293

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	14.894049	20.008801	12.900278	4.663417	5.640557	13.387719	15.419854	9.589737	2.443978	1.05161

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	13.81277	10.248184	7.02966	12.773099	11.584904	13.070148	11.979979	7.325224	8.21637	3.959661

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	12.577097	18.012404	11.063543	8.081252	7.811066	18.609545	6.259951	5.520247	7.455086	4.60981

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	9.604105	21.552596	18.184593	15.29269	9.3521	11.245832	7.066741	5.294571	1.559641	0.847131

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	19.706591	19.088444	23.580536	16.674808	4.995705	5.782284	2.358054	5.92882	1.436728	0.44803

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	6.758774	19.644839	18.75311	3.440622	2.166176	9.055073	17.474836	15.817674	4.592598	2.296299

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	19.348515	17.523135	8.867221	25.542586	2.713884	6.703242	3.604934	7.976171	5.259741	2.460571

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	19.4154	11.411254	21.29541	10.361702	3.497632	5.72793	5.641342	20.07137	0.0	2.577962

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	10.58816	10.697316	3.41595	16.681649	5.772441	19.90497	4.48825	17.972261	4.706562	5.772441

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	26.706503	12.646749	11.240773	19.676626	7.022847	6.326889	5.384886	4.681898	6.080844	0.231986

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	20.562122	11.374692	9.047778	14.673622	12.2385	6.411964	7.644785	3.05107	12.485434	2.510035

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	17.74099	29.029193	11.44044	8.651679	9.83102	4.670062	5.889152	7.565043	2.592801	2.589621

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	18.24275	19.010947	14.338391	9.665834	9.533321	4.382562	9.281736	4.509314	8.703668	2.331477

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	16.738061	11.134574	18.624996	13.973272	11.059157	7.036411	12.013937	5.025793	0.524903	3.868895

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	16.090342	14.989362	21.924711	7.464622	7.072678	8.565013	7.54419	10.392121	3.5163	2.440663

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	16.10227	28.223351	17.658009	9.76405	14.094109	5.526449	1.571149	2.156708	2.859996	2.043911

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	31.703476	6.883471	17.319604	10.074485	18.63828	7.40619	4.959746	2.428209	0.285672	0.300867

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	10.39821	11.378738	5.400978	15.995293	15.416205	11.535622	11.032669	8.914729	6.46687	3.460687

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	16.200306	12.590525	8.156293	12.430928	11.521465	6.902774	7.752087	12.564059	8.420149	3.461412

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	17.219608	14.286462	18.290831	11.095984	8.128427	8.601949	8.384264	6.502143	4.916255	2.574077

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	9.502017	12.600838	26.054918	12.23821	8.627443	9.075396	13.459898	4.262333	3.971455	0.207493

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	7.248842	22.984748	25.789606	11.735728	6.926343	4.794591	11.450212	2.041511	4.884832	2.143586

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	12.982224	12.906559	10.209866	7.988677	15.50646	14.684893	10.960761	11.410914	1.89625	1.453395

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	26.691375	9.607013	19.414049	0.588305	11.960231	7.847982	7.059654	7.742087	8.877515	0.21179

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	11.898096	6.765584	12.83128	11.275196	6.37598	9.485816	20.763345	10.652296	1.007839	8.944569

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	13.032774	24.691223	11.366302	7.429175	7.754926	8.366651	11.199654	8.11428	5.844997	2.200018

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	19.574239	21.111286	14.253858	10.129501	7.563948	9.794462	2.97293	4.495836	9.645435	0.458504

Station	A	B	C	D	E	F	H	I	J	K
Mixoplankton %	15.616395	24.009744	16.670197	2.991951	3.701546	4.575302	16.241262	13.323448	2.155264	0.714891

How do the number of mixoplankton from west to east change every year?

def mixoplankton_per_station(csv_name):
    
    # Remove Classification columns and groupby Station for entire year
    classified = Classifier(csv_name)
    by_station = classified.mixoplankton_with_header 
    species_columns = by_station.columns.get_level_values(2).isin(['Phylum', 'Genus', 'Species', 'MFT', 'Evidence of mixoplankton activity', 'size class', 'Totals'])
    by_station = by_station.loc[:, ~species_columns]
    by_station.columns = by_station.columns.get_level_values(1)
    by_station = by_station.groupby(by_station.columns.str[0], axis=1).sum()
    totals_station = by_station.sum()
    totals_station = pd.DataFrame(totals_station).reset_index().rename(columns={0: 'Totals', 'index': 'Station'})

    # Get year
    year = re.search(r'\b(\d{4})\b', csv_name).group(1) if re.search(r'\b(\d{4})\b', csv_name) else 'Year not found'

    # Make basemap
    make_basemap(totals_station, (0, 6000000), f'Mixoplankton {year}')

for csv_name in csvs:
    # Get map for each year
    mixoplankton_per_station(csv_name)

Station	A	B	C	D	E	F	H	I	J	K
Totals	5847196	4436520	3342416	3766312	2747844	1865336	3319982	1831104	1758372	1244804

Station	A	B	C	D	E	F	H	I	J	K
Totals	2735304	3814316	2939464	2466772	1780196	3059408	1440600	1224740	1133044	649616

Station	A	B	C	D	E	F	H	I	J	K
Totals	1470216	1287572	1259720	1384284	275572	664312	545468	1253868	266860	237468

Station	A	B	C	D	E	F	H	I	J	K
Totals	3527216	4269276	2095720	2000416	1932876	962016	1261964	1115190	1118480	460944

Station	A	B	C	D	E	F	H	I	J	K
Totals	3297932	3558192	3691336	1807740	2126560	1346400	1097624	1111528	486112	445324

Station	A	B	C	D	E	F	H	I	J	K
Totals	2315544	2033988	2217512	1917388	1599972	1310584	1434268	1338480	964568	412016

Station	A	B	C	D	E	F	H	I	J	K
Totals	1902428	2234012	2081860	1268608	2071828	1883552	1648988	1425820	428912	231836

Station	A	B	C	D	E	F	H	I	J	K
Totals	2773848	3619132	2262876	1533620	1260468	1546072	1485616	1195920	1192224	352880

Depth profile for oxygen concentration in sea water at each station in Summer of 2021

def oxy_depth_narrows():
    # Clean Data
    oxy = pd.read_csv("DEEP_WQ_oxygen_ALL.csv", dtype={'Station': 'str'})
    oxy = oxy[['Station', 'Date', 'depth', 'oxygen_concentration_in_sea_water mg/L']]
    oxy['Date'] = pd.to_datetime(oxy['Date'])
    oxy = oxy[(oxy['Date'] >= '2021-06-20') & (oxy['Date'] <= '2021-09-22')]

    for Station in ['A4', 'B3', '1', '2', 'C1', '3', '4', '5', 'C2', '6', '7', 'D3']:
        oxy_station = oxy[oxy['Station'] == Station]   
        plt.scatter(oxy_station['oxygen_concentration_in_sea_water mg/L'], oxy_station['depth'])
        plt.gca().invert_yaxis()
        plt.xlabel('Oxygen Concentration in Sea Water mg/L')
        plt.ylabel('Depth')
        plt.xticks(np.arange(0, 13, 1)) 
        plt.yticks(np.arange(0, 46, 5)) 
        plt.title(f'Station {Station} LIS Narrows Summer 2021')
        plt.show()

# Get plot for each station
oxy_depth_narrows()

def oxy_depth(year, season):

    # Clean Data
    oxy = pd.read_csv("DEEP_WQ_oxygen_more.csv", dtype={'Station': 'str'})
    oxy =oxy.copy()
    oxy = oxy[['Station', 'Date', 'depth (m)', 'oxygen_concentration_in_sea_water (mg/L)']]
    oxy['Date'] = pd.to_datetime(oxy['Date'])
    oxy = oxy[(oxy['Date'] >= season2timestamp[season][0]) & (oxy['Date'] <= season2timestamp[season][1])]
    oxy = oxy[oxy['Station'].isin(['A4', 'B3', 'C1', 'D3', 'E1', 'F2', 'H4', 'I2', 'J2', 'K2'])]

    for Station in ['A4', 'B3', 'C1', 'D3', 'E1', 'F2', 'H4', 'I2', 'J2', 'K2']:
        oxy_station = oxy[oxy['Station'] == Station]   
        plt.scatter(oxy_station['oxygen_concentration_in_sea_water (mg/L)'], oxy_station['depth (m)'])
        plt.gca().invert_yaxis()
        plt.xlabel('Oxygen Concentration in Sea Water mg/L')
        plt.ylabel('Depth')
        plt.xticks(np.arange(0, 21, 1)) 
        plt.yticks(np.arange(0, 46, 5)) 
        plt.title(f'Station {Station} LIS {season} {year}')
        plt.show()

for year in [2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021]:
    season2timestamp = {'Winter': (f'{year-1}-12-21', f'{year}-03-20'), 'Spring': (f'{year}-03-21', f'{year}-06-20'), 'Summer': (f'{year}-06-21', f'{year}-09-21'), 'Fall': (f'{year}-09-22', f'{year}-12-20')}
    # Get map for each season
    for season in season2timestamp.keys():
        oxy_depth(year, season)

# oxy = pd.read_csv("DEEP_WQ_oxygen_ALL.csv", dtype={'Station': 'str'})
# oxy = oxy[['Station', 'latitude N', 'longitude E']]
# oxy = oxy[oxy['Station'].isin(['1', '2', '3', '4', '5', '6', '7', 'A4', 'B3', 'C1', 'C2', 'D3'])].drop_duplicates().reset_index(drop=True)

# # Create Basemap and color bar
# fig, ax = plt.subplots(figsize=(10, 10))
        
# # Create a Basemap instance
# map = Basemap(projection='cyl', lon_0=-73, lat_0=41, llcrnrlat=40.7, urcrnrlat=41.3, llcrnrlon=-74, urcrnrlon=-72, resolution='f', ax=ax)
    
# # Add map features
# map.drawmapboundary()
# map.fillcontinents()
# map.drawcoastlines()
# map.drawparallels(np.arange(40.7, 41.3, .15), labels=[1, 1, 1, 1])
# map.drawmeridians(np.arange(-74, -72, .25), labels=[1, 1, 1, 1])

# for i in range(len(oxy)):
#     plt.annotate(oxy['Station'][i], (oxy['longitude E'][i], oxy['latitude N'][i]), color='black')

#     # Scatter plot on the Basemap
# map.scatter(oxy['longitude E'], oxy['latitude N'], s=100, zorder=2, color='lime')

# plt.show